Construction of a risk prediction model based on the analysis of MRI imaging features for patients with triple-negative breast cancer and validation of its efficacy

This study is aimed at constructing a risk prediction model for patients with triple-negative breast cancer based on the feature analysis of Magnetic Resonance Imaging (MRI) and verifying the efficacy of the model. 150 patients admitted to our hospital, who had been diagnosed with breast cancer by immunohistochemistry were recruited as our study subjects. For each patient, we collated a range of clinical data (age, tumor size, menopausal status and family history of breast cancer), pathological findings (tumor pathological type and grading), and MRI imaging characteristics. Then patients with triple-negative breast cancer were compared to patients with non-triple-negative cancers. We created a risk prediction model for patients with triple-negative breast cancer after identifying risk variables for the disease using single-factor and multi-factor logistic regression analysis. The Hosmer and Lemeshow test was used to assess the goodness-of-fit of the risk prediction model and a Receiver Operating Characteristic (ROC) curve was plotted by SPSS to evaluate the predictive value of the risk prediction model. The results of single factor analysis based on MRI imaging characteristics showed that there were statistically significant differences between triple-negative breast cancer patients and non-triple-negative breast cancer patients in terms of clear boundaries, increased blood vessels around the tumor, T2-weighted imaging (T2WI) signals, and enhancement mode (p < 0.05). The statistical model for predicting triple-negative breast cancer was: P = 1/[1 + exp(6.055 − 2.802X2 − 1.904X3 − 2.120X4)]. The Hosmer and Lemeshow test was used to test the goodness-of-fit for the statistical model (χ2 = 7.993, p = 0.434). ROC analysis showed that the area under the curve (AUC) was 0.916 and with a 95%confidence interval (CI) of 0.874–0.957.

MRI imaging features; Triple-negative breast cancer patients; Risk prediction model; Efficacy verification

[1] Guo Y, Huang Y, Wang Y, Huang J, Lai Q, Li Y. Breast MRI tumor automatic segmentation and triple-negative breast cancer discrimination algorithm based on deep learning. Computational and Mathematical Methods in Medicine. 2022; 2022: 1–9.

[2] Ma M, Gan L, Liu Y, Jiang Y, Xin L, Liu Y, et al. Radiomics features based on automatic segmented MRI images: prognostic biomarkers for triple-negative breast cancer treated with neoadjuvant chemotherapy. European Journal of Radiology. 2022; 146: 110095.

[3] Matsuda M, Tsuda T, Ebihara R, Toshimori W, Okada K, Takeda S, et al. Triple-negative breast cancer on contrast-enhanced MRI and synthetic MRI: a comparison with non-triple-negative breast carcinoma. European Journal of Radiology. 2021; 142: 109838.

[4] Sha YS, Chen JF. MRI-based radiomics for the diagnosis of triple-negative breast cancer: a meta-analysis. Clinical Radiology. 2022; 77: 655–663.

[5] Li Y, Chen Y, Zhao R, Ji Y, Li J, Zhang Y, et al. Development and validation of a nomogram based on pretreatment dynamic contrast-enhanced MRI for the prediction of pathologic response after neoadjuvant chemotherapy for triple-negative breast cancer. European Radiology. 2022; 32: 1676–1687.

[6] Ma M, Gan L, Jiang Y, Qin N, Li C, Zhang Y, et al. Radiomics analysis based on automatic image segmentation of DCE-MRI for predicting triple-negative and nontriple-negative breast cancer. Computational and Mathematical Methods in Medicine. 2021; 2021: 1–7.

[7] Capozza M, Anemone A, Dhakan C, Della Peruta M, Bracesco M, Zullino S, et al. GlucoCEST MRI for the evaluation response to chemotherapeutic and metabolic treatments in a murine triple-negative breast cancer: a comparison with[18F]F-FDG-PET. Molecular Imaging and Biology. 2022; 24: 126–134.

[8] Jimenez JE, Abdelhafez A, Mittendorf EA, Elshafeey N, Yung JP, Litton JK, et al. A model combining pretreatment MRI radiomic features and tumor-infiltrating lymphocytes to predict response to neoadjuvant systemic therapy in triple-negative breast cancer. European Journal of Radiology. 2022; 149: 110220.

[9] Zhang D, You Y, Xu Y, Cheng Q, Xiao Z, Chen T, et al. Facile synthesis of near-infrared responsive on-demand oxygen releasing nanoplatform for precise MRI-guided theranostics of hypoxia-induced tumor chemoresistance and metastasis in triple negative breast cancer. Journal of Nanobiotechnology. 2022; 20: 104.

[10] Kong QC, Tang WJ, Chen SY, Hu WK, Hu Y, Liang YS, et al. Nomogram for the prediction of triple-negative breast cancer histological heterogeneity based on multiparameter MRI features: a preliminary study including metaplastic carcinoma and non- metaplastic carcinoma. Frontiers in Oncology. 2022; 12: 916988.

[11] Kamiya S, Satake H, Hayashi Y, Ishigaki S, Ito R, Kawamura M, et al. Features from MRI texture analysis associated with survival outcomes in triple-negative breast cancer patients. Breast Cancer. 2022; 29: 164–173.

[12] Xu WJ, Zheng BJ, Lu J, Liu SY, Li HL. Identification of triple-negative breast cancer and androgen receptor expression based on histogram and texture analysis of dynamic contrast-enhanced MRI. BMC Medical Imaging. 2023; 23: 70.

[13] Cheng X, Xia L, Sun S. A pre-operative MRI-based brain metastasis risk-prediction model for triple-negative breast cancer. Gland Surgery. 2021; 10: 2715–2723.

[14] Yamaguchi A, Honda M, Ishiguro H, Kataoka M, Kataoka TR, Shimizu H, et al. Kinetic information from dynamic contrast-enhanced MRI enables prediction of residual cancer burden and prognosis in triple-negative breast cancer: a retrospective study. Scientific Reports. 2021; 11: 10112.

[15] Wu C, Jarrett AM, Zhou Z, Elshafeey N, Adrada BE, Candelaria RP, et al. MRI-based digital models forecast patient-specific treatment responses to neoadjuvant chemotherapy in triple-negative breast cancer. Cancer Research. 2022; 82: 3394–3404.

[16] Abdelhafez AH, Musall BC, Adrada BE, Hess K, Son JB, Hwang K, et al. Tumor necrosis by pretreatment breast MRI: association with neoadjuvant systemic therapy (NAST) response in triple-negative breast cancer (TNBC). Breast Cancer Research and Treatment. 2021; 185: 1–12.

[17] Pineda FD. Editorial for “Functional tumor volume by fast dynamic contrast-enhanced MRI for predicting neoadjuvant systemic therapy response in triple-negative breast cancer”. Journal of Magnetic Resonance Imaging. 2021; 54: 261–262.

[18] Musall BC, Abdelhafez AH, Adrada BE, Candelaria RP, Mohamed RMM, Boge M, et al. Functional tumor volume by fast dynamic contrast-enhanced MRI for predicting neoadjuvant systemic therapy response in triple-negative breast cancer. Journal of Magnetic Resonance Imaging. 2021; 54: 251–260.